Foundations of Machine Learning — Lecture 0 (Course Introduction & Syllabus)

Course Overview

This course introduces core mathematical and algorithmic foundations of machine learning. It balances theory (probability, linear algebra, optimization) with practical implementation (Python, model evaluation). By the end of the course students will be able to design, analyze and implement basic supervised and unsupervised learning algorithms and understand when to apply them.

Prerequisites

Introductory calculus and linear algebra
Basic probability/statistics
Familiarity with Python (numpy/pandas)

Learning Outcomes

Apply linear algebra and probability to ML problems
Implement algorithms: linear/logistic regression, SVM, decision trees, clustering
Perform model evaluation and mitigation (cross-validation, regularization)
Read and interpret ML research at an introductory level

Week-by-week Syllabus

Week	Topics	In-class / Lab
0	Course introduction, syllabus, tools (Python, Jupyter), evaluation	Install + quick Python demo
1	Linear algebra refresher (vectors, matrices, matrix operations)	NumPy matrix ops
2	Probability basics & distributions	Probability exercises
3	Optimization & convexity; gradient descent	Implement GD
4	Linear regression; least squares; normal equations	Linear regression from scratch
5	Logistic regression; binary classification; loss functions	Classification lab
6	Regularization; bias-variance tradeoff; model selection	Cross-validation lab
7	Support Vector Machines & kernels	Kernel demo
8	Decision trees & ensemble methods (bagging, boosting)	Random forest lab
9	Unsupervised learning: k-means, hierarchical clustering, PCA	PCA + clustering lab
10	Neural nets basics; backpropagation	Small NN from scratch
11	Model interpretability & fairness basics	Case studies
12	Course wrap-up; student presentations; project demos	Final presentations

Assessment & Grading

Industry Integrated Project: 35% (typically 8–10 small labs)
Written Exam (theory + coding): 25%
Final Project / Presentation: 25%
Participation / Quizzes: 15%

Notes: Late policy — small penalty per day; academic honesty expected. Projects may be done in groups of up to 3.

Textbooks & Resources

Pattern Recognition and Machine Learning — C. Bishop (recommended chapters)
Introduction to Statistical Learning — James, Witten, Hastie, Tibshirani (free PDF)
Scikit-learn documentation, NumPy & pandas docs, selected research papers (provided on LMS)

Jupyter notebooks, starter code and datasets will be available on the course GitHub / LMS.

Getting started (Lecture 0 lab)

Install Python 3.10+ and create a venv: python -m venv ml-venv && source ml-venv/bin/activate
Install core packages: pip install numpy pandas matplotlib scikit-learn jupyterlab
Open JupyterLab and run the starter notebook Lecture0_GettingStarted.ipynb

Jump to Syllabus